According to a study published in the Proceedings of the National Academy of Sciences on April 15th, 2025, a novel artificial intelligence (AI) tool has revealed how disease-linked proteins misfold into harmful structures, providing a significant advance in understanding neurodegenerative disorders such as Alzheimer’s and Parkinson’s.
Image Credit: tonkid/Shutterstock.com
The study, which was coordinated by Mingchen Chen of the Changping Laboratory and Rice University’s Peter Wolynes, presents RibbonFold, a new computational method for predicting the shapes of amyloids - long, twisted fibers that build in the brains of individuals with neurological decline.
RibbonFold is specifically designed to handle the complex and varied structures of poorly folded proteins rather than functional proteins.
We’ve shown how AI folding codes can be constrained by incorporating a physical understanding of the energy landscape of amyloid fibrils to predict their structures. RibbonFold outperforms other AI-based prediction tools like AlphaFold, which were trained only to predict correctly folded globular protein structures.
Wolynes, the D.R. Bullard-Welch Foundation Professor and Co-Director, Center for Theoretical Biological Physics, Rice University
Eclipsing the Gold Standard
RibbonFold builds on recent developments in AI-based protein structure prediction. Unlike tools like AlphaFold2 and AlphaFold3, which are trained on well-behaved, globular proteins, RibbonFold contains restrictions designed to capture the ribbonlike properties of amyloid fibrils. The researchers trained the model with current structural data on amyloid fibrils before validating it against other known fibril structures that were purposefully removed from the training.
Their findings show that RibbonFold surpasses other AI techniques in this specific domain and shows previously unknown intricacies in how amyloids develop and change in the body. Importantly, it implies that fibrils may start out in one structural form but eventually transition into more insoluble forms, contributing to disease progression.
“Misfolded proteins can take on many different structures. Our method shows that stable polymorphs will likely win out over time by being more insoluble than other forms, explaining the late onset of symptoms. This idea could reshape how researchers approach neurodegenerative disease treatment,” added Wolynes.
New Frontier in Drug Development and Beyond
RibbonFold’s success in predicting amyloid polymorphs may mark a turning point in how scientists can approach neurodegenerative diseases.
Offering a scalable, accurate method for analyzing the structure of harmful protein aggregates, RibbonFold opens new possibilities for drug development. Pharmaceutical researchers can now target drug design by binding to the most disease-relevant fibril structures with greater precision.
This work not only explains a long-standing problem but also equips us with the tools to systematically study and intervene in one of life’s most destructive processes.
Mingchen Chen, Study Co-Corresponding Author, Rice University
These findings go beyond medicine and provide insights into protein self-assembly, which could have implications for synthetic biomaterials. Furthermore, the discovery answers a key structural biology question: why similar proteins can fold into various disease-causing forms.
“The ability to predict amyloid polymorphs efficiently may guide future breakthroughs in preventing harmful protein aggregation, a crucial step toward tackling some of the world’s most pressing neurodegenerative challenges,” concluded Wolynes.
This study's other authors include co-first authors Liangyue Guo and Qilin Yu, as well as Changping Laboratory's Di Wang and Xiaoyu Wu. The National Science Foundation, the Welch Foundation, and the Changping Laboratory helped fund the study.
Journal Reference:
Guo, L., et al. (2025) Generating the polymorph landscapes of amyloid fibrils using AI: RibbonFold. Proceedings of the National Academy of Scienc. doi.org/10.1073/pnas.2501321122